Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1130 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.4572. Min Act: -0.0001

Data Index: 769470 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.5005. Min Act: -0.0001

Data Index: 49426 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.3235. Min Act: -0.0001

Data Index: 274598 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.2501. Min Act: -0.0001

Data Index: 219419 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.2214. Min Act: -0.0001

Data Index: 994913 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.2294. Min Act: -0.0001

Data Index: 286298 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.0857. Min Act: -0.0001

Data Index: 431623 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.2007. Min Act: -0.0001

Data Index: 251161 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.1807. Min Act: -0.0001

Data Index: 754231 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.1507. Min Act: -0.0001

Data Index: 504687 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.0662. Min Act: -0.0001

Data Index: 648834 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.1617. Min Act: -0.0001

Data Index: 1106548 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.1434. Min Act: -0.0001

Data Index: 129912 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.1233. Min Act: -0.0001

Data Index: 1022584 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.0747. Min Act: -0.0001

Data Index: 1347770 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.9664. Min Act: -0.0001

Data Index: 313606 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.0772. Min Act: -0.0001

Data Index: 1271818 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.1554. Min Act: -0.0001

Data Index: 301779 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.1469. Min Act: -0.0001

Data Index: 1116934 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.0753. Min Act: -0.0001

Data Index: 877108 (C4 (Web Text))

Max Activating Token Index: 319